2026-03-07 14:30:36 +00:00
|
|
|
variable "tls_secret_name" {
|
2026-03-14 08:51:45 +00:00
|
|
|
type = string
|
2026-03-07 14:30:36 +00:00
|
|
|
sensitive = true
|
|
|
|
|
}
|
2026-02-22 13:56:34 +00:00
|
|
|
variable "resume_database_url" { type = string }
|
[ci skip] Infrastructure hardening: security, monitoring, reliability, maintainability
Phase 1 - Critical Security:
- Netbox: move hardcoded DB/superuser passwords to variables
- MeshCentral: disable public registration, add Authentik auth
- Traefik: disable insecure API dashboard (api.insecure=false)
- Traefik: configure forwarded headers with Cloudflare trusted IPs
Phase 2 - Security Hardening:
- Add security headers middleware (HSTS, X-Frame-Options, nosniff, etc.)
- Add Kyverno pod security policies in audit mode (privileged, host
namespaces, SYS_ADMIN, trusted registries)
- Tighten rate limiting (avg=10, burst=50)
- Add Authentik protection to grampsweb
Phase 3 - Monitoring & Alerting:
- Add critical service alerts (PostgreSQL, MySQL, Redis, Headscale,
Authentik, Loki)
- Increase Loki retention from 7 to 30 days (720h)
- Add predictive PV filling alert (predict_linear)
- Re-enable Hackmd and Privatebin down alerts
Phase 4 - Reliability:
- Add resource requests/limits to Redis, DBaaS, Technitium, Headscale,
Vaultwarden, Uptime Kuma
- Increase Alloy DaemonSet memory to 512Mi/1Gi
Phase 6 - Maintainability:
- Extract duplicated tiers locals to terragrunt.hcl generate block
(removed from 67 stacks)
- Replace hardcoded NFS IP 10.0.10.15 with var.nfs_server (114
instances across 63 files)
- Replace hardcoded Redis/PostgreSQL/MySQL/Ollama/mail host references
with variables across ~35 stacks
- Migrate xray raw ingress resources to ingress_factory modules
2026-02-23 22:05:28 +00:00
|
|
|
variable "nfs_server" { type = string }
|
|
|
|
|
variable "mail_host" { type = string }
|
2026-02-22 13:56:34 +00:00
|
|
|
|
2026-03-14 17:15:48 +00:00
|
|
|
data "vault_kv_secret_v2" "secrets" {
|
|
|
|
|
mount = "secret"
|
|
|
|
|
name = "resume"
|
|
|
|
|
}
|
2026-02-22 13:56:34 +00:00
|
|
|
|
2026-02-22 15:13:55 +00:00
|
|
|
locals {
|
migrate consuming stacks to ESO + remove k8s-dashboard static token
Phase 9: ExternalSecret migration across 26 stacks:
Fully migrated (vault data source removed, ESO delivers secrets):
- speedtest, shadowsocks, wealthfolio, plotting-book, f1-stream, tandoor
- n8n, dawarich, diun, netbox, onlyoffice, tuya-bridge
- hackmd (ESO template for DB URL), health (ESO template for DB URL)
- trading-bot (ESO template for DATABASE_URL + 7 secret env vars)
- forgejo (removed unused vault data source)
Partially migrated (vault kept for plan-time, ESO added for runtime):
- immich, linkwarden, nextcloud, paperless-ngx (jsondecode for homepage)
- claude-memory, rybbit, url, webhook_handler (plan-time in locals/jobs)
- woodpecker, openclaw, resume (plan-time in helm values/jobs/modules)
17 stacks unchanged (all plan-time: homepage annotations, configmaps,
module inputs) — vault data source works with OIDC auth.
Phase 17a: Remove k8s-dashboard static admin token secret.
Users now get tokens via: vault write kubernetes/creds/dashboard-admin
2026-03-15 19:05:04 +00:00
|
|
|
namespace = "resume"
|
|
|
|
|
app_url = "https://resume.viktorbarzin.me"
|
2026-03-14 17:15:48 +00:00
|
|
|
mailserver_accounts = jsondecode(data.vault_kv_secret_v2.secrets.data["mailserver_accounts"])
|
2026-02-22 15:13:55 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
resource "kubernetes_namespace" "resume" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = local.namespace
|
|
|
|
|
labels = {
|
|
|
|
|
tier = local.tiers.aux
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
module "tls_secret" {
|
|
|
|
|
source = "../../modules/kubernetes/setup_tls_secret"
|
|
|
|
|
namespace = kubernetes_namespace.resume.metadata[0].name
|
|
|
|
|
tls_secret_name = var.tls_secret_name
|
|
|
|
|
}
|
|
|
|
|
|
migrate consuming stacks to ESO + remove k8s-dashboard static token
Phase 9: ExternalSecret migration across 26 stacks:
Fully migrated (vault data source removed, ESO delivers secrets):
- speedtest, shadowsocks, wealthfolio, plotting-book, f1-stream, tandoor
- n8n, dawarich, diun, netbox, onlyoffice, tuya-bridge
- hackmd (ESO template for DB URL), health (ESO template for DB URL)
- trading-bot (ESO template for DATABASE_URL + 7 secret env vars)
- forgejo (removed unused vault data source)
Partially migrated (vault kept for plan-time, ESO added for runtime):
- immich, linkwarden, nextcloud, paperless-ngx (jsondecode for homepage)
- claude-memory, rybbit, url, webhook_handler (plan-time in locals/jobs)
- woodpecker, openclaw, resume (plan-time in helm values/jobs/modules)
17 stacks unchanged (all plan-time: homepage annotations, configmaps,
module inputs) — vault data source works with OIDC auth.
Phase 17a: Remove k8s-dashboard static admin token secret.
Users now get tokens via: vault write kubernetes/creds/dashboard-admin
2026-03-15 19:05:04 +00:00
|
|
|
resource "kubernetes_manifest" "external_secret" {
|
|
|
|
|
manifest = {
|
|
|
|
|
apiVersion = "external-secrets.io/v1beta1"
|
|
|
|
|
kind = "ExternalSecret"
|
|
|
|
|
metadata = {
|
|
|
|
|
name = "resume-secrets"
|
|
|
|
|
namespace = "resume"
|
|
|
|
|
}
|
|
|
|
|
spec = {
|
|
|
|
|
refreshInterval = "15m"
|
|
|
|
|
secretStoreRef = {
|
|
|
|
|
name = "vault-kv"
|
|
|
|
|
kind = "ClusterSecretStore"
|
|
|
|
|
}
|
|
|
|
|
target = {
|
|
|
|
|
name = "resume-secrets"
|
|
|
|
|
}
|
|
|
|
|
dataFrom = [{
|
|
|
|
|
extract = {
|
|
|
|
|
key = "resume"
|
|
|
|
|
}
|
|
|
|
|
}]
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
depends_on = [kubernetes_namespace.resume]
|
|
|
|
|
}
|
|
|
|
|
|
2026-02-22 15:13:55 +00:00
|
|
|
# Printer service (browserless chromium for PDF generation)
|
|
|
|
|
resource "kubernetes_deployment" "printer" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = "printer"
|
|
|
|
|
namespace = kubernetes_namespace.resume.metadata[0].name
|
|
|
|
|
labels = {
|
|
|
|
|
app = "printer"
|
|
|
|
|
tier = local.tiers.aux
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
spec {
|
Add node hang instrumentation and scale down chromium services
- Add journald collection to Alloy (loki.source.journal) for kernel OOM,
panic, hung task, and soft lockup detection — ships system logs off-node
so they survive hard resets
- Add 5 Loki alerting rules (KernelOOMKiller, KernelPanic, KernelHungTask,
KernelSoftLockup, ContainerdDown) evaluating against node-journal logs
- Fix Loki ruler config: correct rules mount path (/var/loki/rules/fake),
add alertmanager_url and enable_api
- Add Prometheus alerts: NodeMemoryPressureTrending (>85%), NodeExporterDown,
NodeHighIOWait (>30%)
- Add caretta tolerations for control-plane and GPU nodes
- Scale down chromium-based services to 0 for cluster stability:
f1-stream, flaresolverr, changedetection, resume/printer
2026-03-11 22:46:33 +00:00
|
|
|
replicas = 0 # Scaled down — browserless chromium causes node OOM
|
2026-02-22 15:13:55 +00:00
|
|
|
selector {
|
|
|
|
|
match_labels = {
|
|
|
|
|
app = "printer"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
template {
|
|
|
|
|
metadata {
|
|
|
|
|
labels = {
|
|
|
|
|
app = "printer"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
spec {
|
|
|
|
|
container {
|
|
|
|
|
name = "printer"
|
|
|
|
|
image = "ghcr.io/browserless/chromium:latest"
|
|
|
|
|
|
|
|
|
|
port {
|
|
|
|
|
container_port = 3000
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
env {
|
|
|
|
|
name = "HEALTH"
|
|
|
|
|
value = "true"
|
|
|
|
|
}
|
|
|
|
|
env {
|
|
|
|
|
name = "CONCURRENT"
|
|
|
|
|
value = "20"
|
|
|
|
|
}
|
|
|
|
|
env {
|
|
|
|
|
name = "QUEUED"
|
|
|
|
|
value = "10"
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
resources {
|
|
|
|
|
requests = {
|
2026-02-28 21:59:08 +00:00
|
|
|
memory = "128Mi"
|
[ci skip] right-size all pod resources based on VPA + live metrics audit
Full cluster resource audit: cross-referenced Goldilocks VPA recommendations,
live kubectl top metrics, and Terraform definitions for 100+ containers.
Critical fixes:
- dashy: CPU throttled at 98% (490m/500m) → 2 CPU limit
- stirling-pdf: CPU throttled at 99.7% (299m/300m) → 2 CPU limit
- traefik auth-proxy/bot-block-proxy: mem limit 32Mi → 128Mi
Added explicit resources to ~40 containers that had none:
- audiobookshelf, changedetection, cyberchef, dawarich, diun, echo,
excalidraw, freshrss, hackmd, isponsorblocktv, linkwarden, n8n,
navidrome, ntfy, owntracks, privatebin, send, shadowsocks, tandoor,
tor-proxy, wealthfolio, networking-toolbox, rybbit, mailserver,
cloudflared, pgadmin, phpmyadmin, crowdsec-web, xray, wireguard,
k8s-portal, tuya-bridge, ollama-ui, whisper, piper, immich-server,
immich-postgresql, osrm-foot
GPU containers: added CPU/mem alongside GPU limits:
- ollama: removed CPU/mem limits (models vary in size), keep GPU only
- frigate: req 500m/2Gi, lim 4/8Gi + GPU
- immich-ml: req 100m/1Gi, lim 2/4Gi + GPU
Right-sized ~25 over-provisioned containers:
- kms-web-page: 500m/512Mi → 50m/64Mi (was using 0m/10Mi)
- onlyoffice: CPU 8 → 2 (VPA upper 45m)
- realestate-crawler-api: CPU 2000m → 250m
- blog/travel-blog/webhook-handler: 500m → 100m
- coturn/health/plotting-book: reduced to match actual usage
Conservative methodology: limits = max(VPA upper * 2, live usage * 2)
2026-03-01 19:18:50 +00:00
|
|
|
cpu = "25m"
|
2026-02-22 15:13:55 +00:00
|
|
|
}
|
|
|
|
|
limits = {
|
right-size memory: set requests=limits based on actual usage
- Set memory requests = limits across 56 stacks to prevent overcommit
- Right-sized limits based on actual pod usage (2x actual, rounded up)
- Scaled down trading-bot (replicas=0) to free memory
- Fixed OOMKilled services: forgejo, dawarich, health, meshcentral,
paperless-ngx, vault auto-unseal, rybbit, whisper, openclaw, clickhouse
- Added startup+liveness probes to calibre-web
- Bumped inotify limits on nodes 2,3 (max_user_instances 128->8192)
Post node2 OOM incident (2026-03-14). Previous kubelet config had no
kubeReserved/systemReserved set, allowing pods to starve the kernel.
2026-03-14 21:01:24 +00:00
|
|
|
memory = "128Mi"
|
2026-02-22 15:13:55 +00:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
liveness_probe {
|
|
|
|
|
http_get {
|
|
|
|
|
path = "/pressure"
|
|
|
|
|
port = 3000
|
|
|
|
|
}
|
|
|
|
|
initial_delay_seconds = 30
|
|
|
|
|
period_seconds = 10
|
|
|
|
|
timeout_seconds = 5
|
|
|
|
|
}
|
|
|
|
|
readiness_probe {
|
|
|
|
|
http_get {
|
|
|
|
|
path = "/pressure"
|
|
|
|
|
port = 3000
|
|
|
|
|
}
|
|
|
|
|
initial_delay_seconds = 10
|
|
|
|
|
period_seconds = 10
|
|
|
|
|
timeout_seconds = 5
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
resource "kubernetes_service" "printer" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = "printer"
|
|
|
|
|
namespace = kubernetes_namespace.resume.metadata[0].name
|
|
|
|
|
}
|
|
|
|
|
spec {
|
|
|
|
|
selector = {
|
|
|
|
|
app = "printer"
|
|
|
|
|
}
|
|
|
|
|
port {
|
|
|
|
|
port = 3000
|
|
|
|
|
target_port = 3000
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2026-03-01 23:42:23 +00:00
|
|
|
module "nfs_data" {
|
|
|
|
|
source = "../../modules/kubernetes/nfs_volume"
|
|
|
|
|
name = "resume-data"
|
|
|
|
|
namespace = kubernetes_namespace.resume.metadata[0].name
|
|
|
|
|
nfs_server = var.nfs_server
|
|
|
|
|
nfs_path = "/mnt/main/resume"
|
|
|
|
|
}
|
|
|
|
|
|
2026-02-22 15:13:55 +00:00
|
|
|
# Reactive Resume app
|
|
|
|
|
resource "kubernetes_deployment" "resume" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = "resume"
|
|
|
|
|
namespace = kubernetes_namespace.resume.metadata[0].name
|
|
|
|
|
labels = {
|
|
|
|
|
app = "resume"
|
|
|
|
|
tier = local.tiers.aux
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
spec {
|
Add node hang instrumentation and scale down chromium services
- Add journald collection to Alloy (loki.source.journal) for kernel OOM,
panic, hung task, and soft lockup detection — ships system logs off-node
so they survive hard resets
- Add 5 Loki alerting rules (KernelOOMKiller, KernelPanic, KernelHungTask,
KernelSoftLockup, ContainerdDown) evaluating against node-journal logs
- Fix Loki ruler config: correct rules mount path (/var/loki/rules/fake),
add alertmanager_url and enable_api
- Add Prometheus alerts: NodeMemoryPressureTrending (>85%), NodeExporterDown,
NodeHighIOWait (>30%)
- Add caretta tolerations for control-plane and GPU nodes
- Scale down chromium-based services to 0 for cluster stability:
f1-stream, flaresolverr, changedetection, resume/printer
2026-03-11 22:46:33 +00:00
|
|
|
replicas = 0 # Scaled down with printer — depends on browserless chromium
|
2026-02-22 15:13:55 +00:00
|
|
|
selector {
|
|
|
|
|
match_labels = {
|
|
|
|
|
app = "resume"
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
template {
|
|
|
|
|
metadata {
|
|
|
|
|
labels = {
|
|
|
|
|
app = "resume"
|
|
|
|
|
}
|
migrate consuming stacks to ESO + remove k8s-dashboard static token
Phase 9: ExternalSecret migration across 26 stacks:
Fully migrated (vault data source removed, ESO delivers secrets):
- speedtest, shadowsocks, wealthfolio, plotting-book, f1-stream, tandoor
- n8n, dawarich, diun, netbox, onlyoffice, tuya-bridge
- hackmd (ESO template for DB URL), health (ESO template for DB URL)
- trading-bot (ESO template for DATABASE_URL + 7 secret env vars)
- forgejo (removed unused vault data source)
Partially migrated (vault kept for plan-time, ESO added for runtime):
- immich, linkwarden, nextcloud, paperless-ngx (jsondecode for homepage)
- claude-memory, rybbit, url, webhook_handler (plan-time in locals/jobs)
- woodpecker, openclaw, resume (plan-time in helm values/jobs/modules)
17 stacks unchanged (all plan-time: homepage annotations, configmaps,
module inputs) — vault data source works with OIDC auth.
Phase 17a: Remove k8s-dashboard static admin token secret.
Users now get tokens via: vault write kubernetes/creds/dashboard-admin
2026-03-15 19:05:04 +00:00
|
|
|
annotations = {
|
|
|
|
|
"reloader.stakater.com/search" = "true"
|
|
|
|
|
}
|
2026-02-22 15:13:55 +00:00
|
|
|
}
|
|
|
|
|
spec {
|
|
|
|
|
container {
|
|
|
|
|
name = "resume"
|
|
|
|
|
image = "amruthpillai/reactive-resume:v5.0.3"
|
|
|
|
|
|
|
|
|
|
port {
|
|
|
|
|
container_port = 3000
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
# Required env vars
|
|
|
|
|
env {
|
|
|
|
|
name = "APP_URL"
|
|
|
|
|
value = local.app_url
|
|
|
|
|
}
|
|
|
|
|
env {
|
|
|
|
|
name = "DATABASE_URL"
|
|
|
|
|
value = var.resume_database_url
|
|
|
|
|
}
|
|
|
|
|
env {
|
|
|
|
|
name = "PRINTER_ENDPOINT"
|
|
|
|
|
value = "ws://printer.${local.namespace}.svc.cluster.local:3000"
|
|
|
|
|
}
|
|
|
|
|
env {
|
|
|
|
|
name = "PRINTER_APP_URL"
|
|
|
|
|
value = "http://resume.${local.namespace}.svc.cluster.local"
|
|
|
|
|
}
|
|
|
|
|
env {
|
migrate consuming stacks to ESO + remove k8s-dashboard static token
Phase 9: ExternalSecret migration across 26 stacks:
Fully migrated (vault data source removed, ESO delivers secrets):
- speedtest, shadowsocks, wealthfolio, plotting-book, f1-stream, tandoor
- n8n, dawarich, diun, netbox, onlyoffice, tuya-bridge
- hackmd (ESO template for DB URL), health (ESO template for DB URL)
- trading-bot (ESO template for DATABASE_URL + 7 secret env vars)
- forgejo (removed unused vault data source)
Partially migrated (vault kept for plan-time, ESO added for runtime):
- immich, linkwarden, nextcloud, paperless-ngx (jsondecode for homepage)
- claude-memory, rybbit, url, webhook_handler (plan-time in locals/jobs)
- woodpecker, openclaw, resume (plan-time in helm values/jobs/modules)
17 stacks unchanged (all plan-time: homepage annotations, configmaps,
module inputs) — vault data source works with OIDC auth.
Phase 17a: Remove k8s-dashboard static admin token secret.
Users now get tokens via: vault write kubernetes/creds/dashboard-admin
2026-03-15 19:05:04 +00:00
|
|
|
name = "AUTH_SECRET"
|
|
|
|
|
value_from {
|
|
|
|
|
secret_key_ref {
|
|
|
|
|
name = "resume-secrets"
|
|
|
|
|
key = "auth_secret"
|
|
|
|
|
}
|
|
|
|
|
}
|
2026-02-22 15:13:55 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
# Server config
|
|
|
|
|
env {
|
|
|
|
|
name = "TZ"
|
|
|
|
|
value = "Etc/UTC"
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
# SMTP config for password reset emails
|
|
|
|
|
env {
|
|
|
|
|
name = "SMTP_HOST"
|
[ci skip] Infrastructure hardening: security, monitoring, reliability, maintainability
Phase 1 - Critical Security:
- Netbox: move hardcoded DB/superuser passwords to variables
- MeshCentral: disable public registration, add Authentik auth
- Traefik: disable insecure API dashboard (api.insecure=false)
- Traefik: configure forwarded headers with Cloudflare trusted IPs
Phase 2 - Security Hardening:
- Add security headers middleware (HSTS, X-Frame-Options, nosniff, etc.)
- Add Kyverno pod security policies in audit mode (privileged, host
namespaces, SYS_ADMIN, trusted registries)
- Tighten rate limiting (avg=10, burst=50)
- Add Authentik protection to grampsweb
Phase 3 - Monitoring & Alerting:
- Add critical service alerts (PostgreSQL, MySQL, Redis, Headscale,
Authentik, Loki)
- Increase Loki retention from 7 to 30 days (720h)
- Add predictive PV filling alert (predict_linear)
- Re-enable Hackmd and Privatebin down alerts
Phase 4 - Reliability:
- Add resource requests/limits to Redis, DBaaS, Technitium, Headscale,
Vaultwarden, Uptime Kuma
- Increase Alloy DaemonSet memory to 512Mi/1Gi
Phase 6 - Maintainability:
- Extract duplicated tiers locals to terragrunt.hcl generate block
(removed from 67 stacks)
- Replace hardcoded NFS IP 10.0.10.15 with var.nfs_server (114
instances across 63 files)
- Replace hardcoded Redis/PostgreSQL/MySQL/Ollama/mail host references
with variables across ~35 stacks
- Migrate xray raw ingress resources to ingress_factory modules
2026-02-23 22:05:28 +00:00
|
|
|
value = var.mail_host
|
2026-02-22 15:13:55 +00:00
|
|
|
}
|
|
|
|
|
env {
|
|
|
|
|
name = "SMTP_PORT"
|
|
|
|
|
value = "587"
|
|
|
|
|
}
|
|
|
|
|
env {
|
|
|
|
|
name = "SMTP_USER"
|
|
|
|
|
value = "info@viktorbarzin.me"
|
|
|
|
|
}
|
|
|
|
|
env {
|
|
|
|
|
name = "SMTP_PASS"
|
2026-03-14 17:15:48 +00:00
|
|
|
value = local.mailserver_accounts["info@viktorbarzin.me"]
|
2026-02-22 15:13:55 +00:00
|
|
|
}
|
|
|
|
|
env {
|
|
|
|
|
name = "SMTP_FROM"
|
|
|
|
|
value = "Reactive Resume <info@viktorbarzin.me>"
|
|
|
|
|
}
|
|
|
|
|
env {
|
|
|
|
|
name = "SMTP_SECURE"
|
|
|
|
|
value = "false"
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
# Feature flags
|
|
|
|
|
env {
|
|
|
|
|
name = "FLAG_DISABLE_SIGNUPS"
|
|
|
|
|
value = "false" # toggle me
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
volume_mount {
|
|
|
|
|
name = "data"
|
|
|
|
|
mount_path = "/app/data"
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
resources {
|
|
|
|
|
requests = {
|
[ci skip] right-size all pod resources based on VPA + live metrics audit
Full cluster resource audit: cross-referenced Goldilocks VPA recommendations,
live kubectl top metrics, and Terraform definitions for 100+ containers.
Critical fixes:
- dashy: CPU throttled at 98% (490m/500m) → 2 CPU limit
- stirling-pdf: CPU throttled at 99.7% (299m/300m) → 2 CPU limit
- traefik auth-proxy/bot-block-proxy: mem limit 32Mi → 128Mi
Added explicit resources to ~40 containers that had none:
- audiobookshelf, changedetection, cyberchef, dawarich, diun, echo,
excalidraw, freshrss, hackmd, isponsorblocktv, linkwarden, n8n,
navidrome, ntfy, owntracks, privatebin, send, shadowsocks, tandoor,
tor-proxy, wealthfolio, networking-toolbox, rybbit, mailserver,
cloudflared, pgadmin, phpmyadmin, crowdsec-web, xray, wireguard,
k8s-portal, tuya-bridge, ollama-ui, whisper, piper, immich-server,
immich-postgresql, osrm-foot
GPU containers: added CPU/mem alongside GPU limits:
- ollama: removed CPU/mem limits (models vary in size), keep GPU only
- frigate: req 500m/2Gi, lim 4/8Gi + GPU
- immich-ml: req 100m/1Gi, lim 2/4Gi + GPU
Right-sized ~25 over-provisioned containers:
- kms-web-page: 500m/512Mi → 50m/64Mi (was using 0m/10Mi)
- onlyoffice: CPU 8 → 2 (VPA upper 45m)
- realestate-crawler-api: CPU 2000m → 250m
- blog/travel-blog/webhook-handler: 500m → 100m
- coturn/health/plotting-book: reduced to match actual usage
Conservative methodology: limits = max(VPA upper * 2, live usage * 2)
2026-03-01 19:18:50 +00:00
|
|
|
memory = "64Mi"
|
|
|
|
|
cpu = "15m"
|
2026-02-22 15:13:55 +00:00
|
|
|
}
|
|
|
|
|
limits = {
|
right-size memory: set requests=limits based on actual usage
- Set memory requests = limits across 56 stacks to prevent overcommit
- Right-sized limits based on actual pod usage (2x actual, rounded up)
- Scaled down trading-bot (replicas=0) to free memory
- Fixed OOMKilled services: forgejo, dawarich, health, meshcentral,
paperless-ngx, vault auto-unseal, rybbit, whisper, openclaw, clickhouse
- Added startup+liveness probes to calibre-web
- Bumped inotify limits on nodes 2,3 (max_user_instances 128->8192)
Post node2 OOM incident (2026-03-14). Previous kubelet config had no
kubeReserved/systemReserved set, allowing pods to starve the kernel.
2026-03-14 21:01:24 +00:00
|
|
|
memory = "64Mi"
|
2026-02-22 15:13:55 +00:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
liveness_probe {
|
|
|
|
|
http_get {
|
|
|
|
|
path = "/api/health"
|
|
|
|
|
port = 3000
|
|
|
|
|
}
|
|
|
|
|
initial_delay_seconds = 60
|
|
|
|
|
period_seconds = 30
|
|
|
|
|
timeout_seconds = 10
|
|
|
|
|
}
|
|
|
|
|
readiness_probe {
|
|
|
|
|
http_get {
|
|
|
|
|
path = "/api/health"
|
|
|
|
|
port = 3000
|
|
|
|
|
}
|
|
|
|
|
initial_delay_seconds = 30
|
|
|
|
|
period_seconds = 10
|
|
|
|
|
timeout_seconds = 5
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
volume {
|
|
|
|
|
name = "data"
|
2026-03-01 23:42:23 +00:00
|
|
|
persistent_volume_claim {
|
|
|
|
|
claim_name = module.nfs_data.claim_name
|
2026-02-22 15:13:55 +00:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
resource "kubernetes_service" "resume" {
|
|
|
|
|
metadata {
|
|
|
|
|
name = "resume"
|
|
|
|
|
namespace = kubernetes_namespace.resume.metadata[0].name
|
|
|
|
|
}
|
|
|
|
|
spec {
|
|
|
|
|
selector = {
|
|
|
|
|
app = "resume"
|
|
|
|
|
}
|
|
|
|
|
port {
|
|
|
|
|
port = 80
|
|
|
|
|
target_port = 3000
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
module "ingress" {
|
|
|
|
|
source = "../../modules/kubernetes/ingress_factory"
|
|
|
|
|
namespace = kubernetes_namespace.resume.metadata[0].name
|
|
|
|
|
name = "resume"
|
|
|
|
|
tls_secret_name = var.tls_secret_name
|
2026-03-07 16:41:36 +00:00
|
|
|
extra_annotations = {
|
|
|
|
|
"gethomepage.dev/enabled" = "true"
|
|
|
|
|
"gethomepage.dev/name" = "Resume"
|
|
|
|
|
"gethomepage.dev/description" = "Online resume"
|
2026-03-07 21:14:17 +00:00
|
|
|
"gethomepage.dev/icon" = "mdi-file-account"
|
2026-03-07 16:41:36 +00:00
|
|
|
"gethomepage.dev/group" = "Other"
|
|
|
|
|
"gethomepage.dev/pod-selector" = ""
|
|
|
|
|
}
|
2026-02-22 13:56:34 +00:00
|
|
|
}
|